A Bayesian Approach to Identifying Representational Errors

03/28/2021
by   Ramya Ramakrishnan, et al.
0

Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand. Determining the root cause for these errors can improve future decisions. This work presents Generative Error Model (GEM), a generative model for inferring representational errors based on observations of an actor's behavior (either simulated agent, robot, or human). The model considers two sources of error: those that occur due to representational limitations – "blind spots" – and non-representational errors, such as those caused by noise in execution or systematic errors present in the actor's policy. Disambiguating these two error types allows for targeted refinement of the actor's policy (i.e., representational errors require perceptual augmentation, while other errors can be reduced through methods such as improved training or attention support). We present a Bayesian inference algorithm for GEM and evaluate its utility in recovering representational errors on multiple domains. Results show that our approach can recover blind spots of both reinforcement learning agents as well as human users.

READ FULL TEXT

page 1

page 5

research
05/23/2018

Discovering Blind Spots in Reinforcement Learning

Agents trained in simulation may make errors in the real world due to mi...
research
11/19/2018

Reinforcement learning and inverse reinforcement learning with system 1 and system 2

Inferring a person's goal from their behavior is an important problem in...
research
09/15/2021

Synthesizing Policies That Account For Human Execution Errors Caused By State-Aliasing In Markov Decision Processes

When humans are given a policy to execute, there can be policy execution...
research
09/06/2019

Automatic Failure Recovery for End-User Programs on Service Mobile Robots

For service mobile robots to be most effective, it must be possible for ...
research
10/20/2020

Survivable Hyper-Redundant Robotic Arm with Bayesian Policy Morphing

In this paper we present a Bayesian reinforcement learning framework tha...
research
10/01/2021

Dynamics of targeted ransomware negotiations

In this paper, we consider how the development of targeted ransomware ha...
research
03/16/2023

ESCAPE: Countering Systematic Errors from Machine's Blind Spots via Interactive Visual Analysis

Classification models learn to generalize the associations between data ...

Please sign up or login with your details

Forgot password? Click here to reset